I'm a data engineer and ML practitioner who turns raw, messy data into reliable pipelines, intelligent models, and clear decisions. I specialize in building scalable data systems and applying machine learning where it actually matters. My work spans Python-based ETL pipelines, cloud infrastructure on AWS, and end-to-end ML deployments. I approach every project with an engineering mindset: clean architecture, reproducible results, and outcomes you can measure.
Currently pursuing my MS in Management Information Systems at UIC, conducting independent research on agentic AI systems under Professor Selvaprabu Nadarajah, and actively seeking full-time roles in data engineering, data science, ML engineering, and AI.
Data Analyst (Graduate Hourly) · University of Illinois Chicago, Online Programs Team · Aug 2024 – Present
Built and deployed ML models to understand enrollment patterns and retention risk, then stuck around to make sure they actually kept working. Set up monitoring frameworks so trends didn't sneak up on anyone, and got comfortable explaining what the numbers meant to people who cared about the outcome, not the model.
Associate Software Developer · PlanSource (Benefits Administration Platform) · Aug 2022 – Aug 2024
Spent 2 years at a company where data actually mattered — benefits administration means every number has a person behind it. Built pipelines that had to be reliable, translated messy real-world data into something systems could actually use, and worked closely with PMs and analysts to understand what the data needed to say. Left with a solid instinct for when data is trustworthy, when it isn't, and what to do about it.
|
Full-stack ML application for predicting and analyzing customer churn. Interactive dashboards, real-time prediction serving, and model explainability.
|
RAG-based system for intelligent document search, summarization, and Q&A. Focused on chunking strategies, retrieval accuracy, and multi-format ingestion.
|
|
End-to-end experimentation framework covering test design, power analysis, statistical inference, and guardrail metrics for product and growth teams.
|
Applied causal inference methods to clinical ICU data for analyzing treatment effects on sepsis outcomes using propensity score matching and doubly robust estimation.
|
|
Prototypes exploring agentic AI under faculty supervision. DSPy pipelines, RAG with ChromaDB, web scraping agents, and n8n workflow automation.
|
Peer-reviewed research applying ML to physiological signal data for stress detection. Published December 2022 with 85% prediction accuracy.
|
Languages: Python · SQL · R · JavaScript · C++
ML & Data Science: scikit-learn · XGBoost · SHAP · TensorFlow · PyTorch · statsmodels · Causal Inference
GenAI & NLP: LangChain · DSPy · ChromaDB · RAG Architectures · Prompt Engineering · n8n
Data Engineering: PostgreSQL · MongoDB · Apache Spark · ETL Pipelines · Data Modeling
Cloud & Infrastructure: AWS (S3, EC2, Lambda, Glue, RDS) · Azure · GCP · Docker · CI/CD
Visualization: Tableau · Power BI · Plotly · Streamlit · Matplotlib
MS in Management Information Systems · University of Illinois Chicago (2024 – 2026)
BE in Electronics & Communication · Dayananda Sagar University (2018 – 2022)